Gyorgy

If you've been enjoying the higher Claude Code limits, tomorrow is the last day before they're gone, along with Fable access. Sonnet 5 pricing also increases from $2/$10 to $3/$15 at the end of August, meaning every prompt burns through your usage budget faster.

@Labeeb_Hameed haha kinda. the cycle never ends, same goals different tools. knowing both is a better advantage than just saying "make no mistakes" 😂

@gyorgysh haha so it all comes down back to us learning how to use ai for it to write code for use(so that we dont have to learn it)

I spent my first days with Claude Code quietly making it slower and more expensive. None of it was the tool. It was my habits. Each has a simple fix. Wrote them all up, worst first.

You're right, and I'm already doing that. But not with the Browser in the desktop app to automatically open a specific project in the desktop app's browser. I mostly use the CLI, so all the automation I commented on is really about getting more flexibility from this newly added feature.

@gyorgysh @ClaudeDevs You can easily instruct these things in your claude.md

Claude Code on desktop now has an in-app browser. Claude can pull up docs, designs, or any other site. It can read, click through, and interact the same way it does with your local dev servers. It's sandboxed and configurable: you choose whether sessions persist.

Full write-up: gyorgy.sh/blog/claude-co…

But it's becoming pay-to-win. The smartest cloud models are a day/night difference over self-hosted or budget ones, and that gap decides what you can build. As a solo builder or small team, the best model you can afford is your real ceiling.

And the role is shifting with it. Every senior engineer is becoming a project manager now, directing and training AI on their own repos. Less typing, more deciding what good looks like.

Agentic coding is quietly becoming the new IDE. A year ago AI was a chat window you copy-pasted from. Now it reads the repo, writes, runs tests, fixes itself. 10x output, same hours. It still needs tuning for smarter indexes, local memory, references that push the model to refactor rather than pile on more bloat. Lots of room to grow.

Keepresso becoming more than a keep-awake app. It fixes headless display issues, kills gaming lag, keeps your Slack status active, and a bunch of other smart triggers on top ☕️

✏️ build on: Claude Code. Grok CLI, Codex CLI, and local models work too (Ollama, LM Studio). 🔈 music: Blast by Aylex (freetouse) ℹ️ source: github.com/gyorgysh/myage… 🎙 full story: > gyorgy.sh/blog/myagens install is one line, grab it at MyAgens.com

📊 the web panel adds live system graphs, a task board that delegates to agents, browsable memory, an encrypted vault, and a feed showing every diff as agents write code.

a while back I wired Claude Code to a Telegram bot so I could fix my server from my phone. then I kept adding one more thing. today it's MyAgens: a self-hosted fleet of AI agents that lives on your machine. open source🫰

free and open source, no license fee, business included. music in the video: All Night by Burgundy (freetouse) keepresso.com

got a Mac mini in a closet? the headless-Mac toolkit probes sleep, auto-restart, auto-login and remote access, and an experimental HiDPI virtual display keeps Screen Sharing crisp with no dummy plug.

You know the move: finger resting on the trackpad so the Mac won't doze off mid agent run 🤖 I built Keepresso instead. a native menu-bar app that keeps your Mac awake on your terms. free, open source, macOS 14+. keepresso.com